Update app.py

app.py

@@ -3,9 +3,9 @@ import pandas as pd
 from pdf2image import convert_from_path
 import pytesseract
 import google.generativeai as genai
-from io import BytesIO
+import tempfile
 
-# Function: Extract text from PDF
+# Function: Extract text from PDF using OCR
 def extract_text_from_pdf(pdf_file):
     pages = convert_from_path(pdf_file)
     all_text = ""
@@ -70,7 +70,7 @@ def generate_mcqs(text, api_key):
         return None, None
 
     df = pd.DataFrame(filtered_mcq_data, columns=["Question", "OptionA", "OptionB", "OptionC", "OptionD", "CorrectAnswer"])
-    return df, df.head(10).to_markdown()  # Show preview
+    return df, df.head(10).to_string(index=False)  # Preview as plain table
 
 # Gradio pipeline
 def process_pdf(pdf_file, api_key):
@@ -84,12 +84,11 @@ def process_pdf(pdf_file, api_key):
         if df is None:
             return "❌ No valid MCQs generated.", None
 
-        # Save to Excel in memory
-        output_file = BytesIO()
-        df.to_excel(output_file, index=False)
-        output_file.seek(0)
+        # Save to a temporary Excel file
+        tmp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".xlsx")
+        df.to_excel(tmp_file.name, index=False)
 
-        return preview, output_file
+        return preview, tmp_file.name
     except Exception as e:
         return f"Error: {str(e)}", None